Expired85% confidenceFactTime unknown
OmniMerge V4 achieved 73.4% on the MBPP code test, an improvement of 15.8 percentage points compared to the original Q6K quantization's 56.2%.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedOmniMerge V4 scored 84.76 on the HumanEval test, on par with the Q6K original version.71% similarUnverifiedDeepSeek V4 Pro achieved a score of 3206 on CodeForces and a pass rate of 95.2% on the MMT-266 benchmark.67% similarUnverifiedQwen3.5's parameter activation rate is 4.3%, while DeepSeek V3's 671B model has an activation rate of 5.5%.67% similarUnverifiedGLM4 scored 74.4% in code reasoning and general knowledge tests, ranking second only to Claude 3 Opus.66% similarUnverifiedWhen using the Mistral 3.8B instruction model with Q4 quantization and native llama.cpp calls, the overall Score improves from 27.3% to 78.3%, with the only difference being whether Forge guardrails are present.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/18009API
curl https://kongchang.com/api/v1/knowledge/claims/18009MCP
get_claim(id=18009)